An Assessment of the Possible Extent of Confounding in Epidemiological Studies of Lung Cancer Risk Among Roofers

Abstract

industry employs about 200,000 workers and estimates indicate about 50,000 on-roof workers are exposed to asphalt fumes during approximately 40% of their working hours. Numerous epidemiological studies have been conducted to evaluate cancer outcomes among roofers, including exposure to asphalt/bitumen fume. However, most studies relied on job title as a surrogate for exposure to asphalt or asphalt fumes because individual exposure data were not available. Therefore, it is unclear whether reported results of an increased risk of lung cancer reflect the direct impact of asphalt exposure on employee health, or if findings are due to bias, such as the presence of other risk factors for lung cancer (i.e., "confounding" exposures) or the use of comparison populations that are inherently different with respect to lung cancer risk. We evaluated the likelihood and extent to which the observed increased risk of lung cancer may be due to confounding (a mixing of effects of multiple exposures) by co-exposure to other potential carcinogens present in roofing or to lifestyle variables. We conducted a review of the epidemiological and industrial hygiene literature of asphalt-exposed workers. Peer-reviewed epidemiological studies of asphalt fumes, related occupational exposures, and confounding factors were identified from MEDLINE (1966-early 2004). Industrial hygiene studies of asphalt workers were identified through MEDLINE, publicly available government documents, and asphalt industry documents. Using wellestablished statistical methods, we quantified the extent to which lung cancer relative risk estimates among roofers reflect confounding from other exposures, using different prevalence and risk scenarios. The relative risk of lung cancer varied from 1.2 to 5.0 in 13 epidemiological studies of roofers; most studies reported a relative risk between 1.2 and 1.4. Smoking, asbestos and coal tar were the most likely confounders, but the prevalence of these factors varied over time. For example, smoking prevalence declined more steadily in the general population than among roofers, and coal tar and asbestos exposures among roofers have declined over the past 50 years. Depending on prevalence estimates used, the relative risk due to confounding ranged from 1.17 to 1.52 (current smoking); 1.36 to 1.78 (asbestos); and 1.04 to 2.32 (coal tar). The results of the study indicate that much of the observed risk reported in epidemiological studies of cancer among roofers is well within the range of what may have resulted from confounding by reasonable and expected levels of smoking, asbestos or coal tar. This may be particularly true for those studies that did not adjust for these confounders and where the exposure was defined as employment in the roofing industry. In addition to poorly defined asphalt exposure, uncontrolled confounding cannot reliably be ruled out in studies of lung cancer among asphalt-exposed roofers. Therefore, it is not possible to conclude whether roofers are at increased risk of lung cancer due to asphalt exposure....

Bayesian modelling of lung cancer risk and bitumen fume exposure adjusted for unmeasured confounding by smoking

“…The association between occupational exposure to bitumen fume during road paving and roofing and excess lung cancer risk has been under discussion for a long time 15 – 22. One reason for this is the uncertainty about the impact of residual confounding on the results of the published studies from co-exposures to other potential carcinogens19 and lifestyle factors, including smoking of tobacco products 17. We will assess data from a multi-centre cohort study that provided evidence that excess lung cancer risk is associated with employment in the asphalt industry20 and may in particular be associated in an exposure-dependent manner with career average exposure to bitumen fume 21.…”

Sensitivity of the association between increased lung cancer risk and bitumen fume exposure to the assumptions in the assessment of exposure

“…Coal tar is considered a potent carcinogen (Straif et al 2005) and although its use in the asphalt industry has declined rapidly from early 1960 to the mid-1970 s , it has been argued that its use as a customary binder in the asphalt mix is the main confounding variable in studies assessing health effect in the roofing and paving industries (Fayerweather 2007;Partanen and Boffetta 1994;Mundt et al 2007). In this study population, workers could have been exposed to coal tar, because some of tem were employed in the years when coal tar was still in use.…”

Meta-Analysis of Lung Cancer in Asphalt Roofing and Paving Workers with External Adjustment for Confounding by Coal Tar

“…(5) Mundt et al's manuscript on confounding in epidemiologic studies of lung cancer risk among roofers. (15) The recent IARC cohort studies of lung cancer mortality and incidence among European asphalt workers. (7) Only peer-reviewed, published manuscripts were eligible for inclusion in the meta-analysis.…”

“…Mundt et al (15) developed prevalence estimates for coal tar use/exposure in U.S. roofers by decade (Table III). The prevalence of coal tar exposure/use among U.S. roofers was an estimated 90% for the 1950s-1960s (based on a small published study of self-reported exposures); 40% for the 1970s (based on National Occupational Health Survey data); and 10% for the 1980s (based on National Occupational Exposure Survey data).…”

“…For example the estimated exposure prevalence for the 50s-1960s (15) was 90% (95% CI = 76%-96%) with a corresponding bias factor of 1.71(95% CI = 1.44-2.02). The 1970s prevalence estimate was 40% (95% CI 26%-55%) with a corresponding bias factor of 1.30 (95% CI 1.13-1.51).…”